v0.2.0

• Abstracted sort_with_host_data from various sort implementations
• Add several inspection methods to the Sorter and Scanner classes
• Fix advanced bitonic sort so it sorts by keys and not directly by values
• Add (unoptimized) Radix sort implementation as described in "Designing Efficient Sorting Algorithms for Manycore GPUs", by Satish et al. (2009)
• Add Park-Miller + TausLCG PRNGs
• Updated to work with cf4ocl 2.1
• Improved documentation build